KEGG
A Model Context Protocol (MCP) server that provides comprehensive access to the KEGG (Kyoto Encyclopedia of Genes and Genomes) database through its REST API.
claude mcp add --transport stdio augmented-nature-kegg-mcp-server npx -y augmented-nature-kegg-mcp-server
How to use
This MCP server provides comprehensive access to KEGG data via a REST-like interface exposed through the MCP SDK. It aggregates KEGG resources such as pathways, genes, compounds, reactions, diseases, drugs, modules, glycans, and BRITE hierarchies, along with advanced analysis tools for cross-references and identifier conversion. The server exposes a suite of tools grouped into categories (Database Information & Statistics, Pathway Analysis, Gene Analysis, Compound Analysis, Reaction & Enzyme Analysis, Disease & Drug Analysis, Module & Orthology Analysis, Glycan Analysis, BRITE Hierarchy Analysis, Advanced Analysis Tools, and Cross-References & Integration). You can perform operations like searching for pathways or genes, retrieving detailed entry information, converting identifiers between KEGG and external databases, and obtaining pathway components or related entries. Use the templates and resource templates to fetch structured data for downstream analysis in bioinformatics workflows.
How to install
Prerequisites:
- Node.js and npm installed on your system
- Git installed for cloning the repository
Installation steps:
- Clone the server repository: git clone https://github.com/augmented-nature/augmented-nature-kegg-mcp-server.git
- Navigate to the server directory: cd augmented-nature-kegg-mcp-server
- Install dependencies: npm install
- Build the server (if applicable): npm run build
- Start the server (development or production): npm start // or run the built entry if a specific script is provided, e.g., node dist/server.js
Note: The project uses the MCP SDK. If you prefer running via npx, you can also start with: npx -y augmented-nature-kegg-mcp-server
Additional notes
Tips and common considerations:
- Ensure your environment has network access to KEGG REST endpoints; some environments may require proxy configuration.
- The server supports batch and streaming-style requests; use batch_entry_lookup for processing multiple KEGG entries efficiently.
- If you encounter timeouts, adjust timeout settings where supported by the MCP SDK or implement client-side retries with backoff.
- Review the API coverage to understand which KEGG resources are exposed (INFO, LIST, FIND, GET, CONV, LINK) and how to format parameters for each tool.
- Enable caching where appropriate to improve performance for frequently requested entries.
- Check environment variables for API keys or rate-limiting controls if the deployment environment requires them.
- When upgrading, consult the CHANGELOG or Version History for breaking changes in tool availability or data formats.
Related MCP Servers
zen
Selfhosted notes app. Single golang binary, notes stored as markdown within SQLite, full-text search, very low resource usage
MCP -Deepseek_R1
A Model Context Protocol (MCP) server implementation connecting Claude Desktop with DeepSeek's language models (R1/V3)
mcp-fhir
A Model Context Protocol implementation for FHIR
mcp
Inkdrop Model Context Protocol Server
mcp-appium-gestures
This is a Model Context Protocol (MCP) server providing resources and tools for Appium mobile gestures using Actions API..
dubco -npm
The (Unofficial) dubco-mcp-server enables AI assistants to manage Dub.co short links via the Model Context Protocol. It provides three MCP tools: create_link for generating new short URLs, update_link for modifying existing links, and delete_link for removing short links.